Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    raph

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Secondary
    -0.07
    aware
    -0.06
     muscle
    -0.06
     savings
    -0.06
     Dems
    -0.06
    ceived
    -0.06
    Median
    -0.06
     Peninsula
    -0.06
    лі
    -0.06
     pä
    -0.06
    POSITIVE LOGITS
     Appropri
    0.07
    yı
    0.07
    less
    0.07
     bou
    0.06
    jk
    0.06
     �
    0.06
    waitFor
    0.06
    SOR
    0.06
    );

↵
    0.06
     daß
    0.06
    Act Density 0.000%

    No Known Activations